AWS / LLM Infrastructure Engineer for DeepSeek Deployment

We’re looking for an AWS / LLM Infrastructure Engineer to help us evaluate and set up DeepSeek on AWS for an application. The scope would include: * Recommending the right AWS architecture for hosting DeepSeek * Comparing deployment options such as EC2, SageMaker, and Amazon Bedrock * Setting up and optimizing DeepSeek inference on AWS * Advising on GPU requirements, scalability, security, and cost * Helping us plan for handling sensitive data within AWS * Documenting the recommended deployment and ongoing infrastructure requirements Experience with DeepSeek, vLLM, AWS GPU instances, SageMaker, Bedrock would be highly preferred. Please share examples of similar LLM deployments you’ve worked on and briefly describe how you would approach this project.